重大更新！公众号每日速递覆盖arXiv所有方向,涵盖CS|物理|数学|经济|统计|金融|生物|电气等领域。点击查看历史文章列表，可在公众号内订阅#arXiv每日学术速递话题，接收每日推送。点击访问arxivdAIly.com每日更新更及时。 人工智能cs.AI 方向，今日共计43篇
【1】 Simple and Effective Synthesis of Indoor 3D Scenes
标题：简单有效的室内三维场景合成
作者：Jing Yu Koh,Harsh Agrawal,Dhruv Batra,Richard Tucker,Austin Waters,Honglak Lee,Yinfei Yang,Jason Baldridge,Peter Anderson
机构*： Google Research, Georgia Institute of Technology, University of Michigan, Apple
链接：点击下载PDF文件
【2】 Beam Search: Faster and Monotonic
标题：波束搜索：速度更快、单调
作者：Sofia Lemons,Carlos Linares López,Robert C. Holte,Wheeler Ruml
机构*： University of New Hampshire, Earlham College, Computer Science and Engineering Department, Universidad Carlos III de Madrid, University of Alberta, Alberta Machine Intelligence Institute (Amii)
备注：9 pages, 15 figures, 3 algorithms, published in the International Conference on Automated Planning and Scheduling ICAPS 2022
链接：点击下载PDF文件
【3】 A survey on recently proposed activation functions for Deep Learning
标题：最近提出的深度学习激活函数研究综述
作者：Murilo Gustineli
备注：7 pages, 2 figures, 15 cited papers
链接：点击下载PDF文件
【4】 Question Generation for Reading Comprehension Assessment by Modeling How and What to Ask
标题：通过建模如何和问什么来生成阅读理解测试的问题
作者：Bilal Ghanem,Lauren Lutz Coleman,Julia Rivard Dexter,Spencer McIntosh von der Ohe,Alona Fyshe
机构*：University of Alberta, Canada, EyeRead, Canada
备注：ACL-2022, 9 pages
链接：点击下载PDF文件
【5】 A Cognitive Framework for Delegation Between Error-Prone AI and Human Agents
标题：一种易出错的人工智能与人类代理之间委托的认知框架
作者：Andrew Fuchs,Andrea Passarella,Marco Conti
机构*：Department of Computer Science, Università di Pisa, National Research Council (CNR), Pisa, Italy, Institute for Informatics and Telematics, accessible.
备注：This work was partially funded by the following projects. European Union's Horizon 2020 research and innovation programme: HumaneAI-Net (No 952026). CHIST-ERA program: SAI project (grant CHIST-ERA-19-XAI-010, funded by MUR, grant number not yet available)
链接：点击下载PDF文件
【6】 PAnDR: Fast Adaptation to New Environments from Offline Experiences via Decoupling Policy and Environment Representations
标题：PANDR：通过分离策略和环境表示，从离线体验快速适应新环境
作者：Tong Sang,Hongyao Tang,Yi Ma,Jianye Hao,Yan Zheng,Zhaopeng Meng,Boyan Li,Zhen Wang
机构*：College of Intelligence and Computing, Tianjin University, School of Artificial Intelligence, Optics and Electronics (iOPEN) and School of, Cybersecurity, Northwestern Polytechnical University
备注：Preprint, work presented at the Generalizable Policy Learning in the Physical World Workshop (ICLR 2022)
链接：点击下载PDF文件
【7】 ECLIPSE: Efficient Long-range Video Retrieval using Sight and Sound
标题：基于视觉和声音的高效远程视频检索
作者：Yan-Bo Lin,Jie Lei,Mohit Bansal,Gedas Bertasius
机构*：University of North Carolina, Chapel Hill
备注：project page: this https URL
链接：点击下载PDF文件
【8】 Demonstrate Once, Imitate Immediately (DOME): Learning Visual Servoing for One-Shot Imitation Learning
标题：演示一次，立即模仿(DOME)：学习视觉伺服，一次模仿学习
作者：Eugene Valassakis,Georgios Papagiannis,Norman Di Palo,Edward Johns
链接：点击下载PDF文件
【9】 KNN-Diffusion: Image Generation via Large-Scale Retrieval
标题：KNN扩散：基于大规模检索的图像生成
作者：Oron Ashual,Shelly Sheynin,Adam Polyak,Uriel Singer,Oran Gafni,Eliya Nachmani,Yaniv Taigman
机构*：Meta AI Research
链接：点击下载PDF文件
【10】 A Transformer-Based Contrastive Learning Approach for Few-Shot Sign Language Recognition
标题：一种基于变换的Few-Shot手语识别对比学习方法
作者：Silvan Ferreira,Esdras Costa,Márcio Dahia,Jampierre Rocha
机构*：CESAR, Recife, Brazil, Lenovo, São Paulo, Brazil
链接：点击下载PDF文件
【11】 Reinforcement Learning Agents in Colonel Blotto
标题：布洛托上校中的强化学习代理
作者：Joseph Christian G. Noel
链接：点击下载PDF文件
【12】 Walk this Way! Entity Walks and Property Walks for RDF2vec
标题：走这边！RDF2vec的实体漫游和属性漫游
作者：Jan Portisch,Heiko Paulheim
机构*： SAP SE, Walldorf, Germany, Data and Web Science Group, University of Mannheim, Germany
备注：accepted at the ESWC Posters and Demos Track
链接：点击下载PDF文件
【13】 Data-Centric Green AI: An Exploratory Empirical Study
标题：以数据为中心的绿色人工智能：探索性实证研究
作者：Roberto Verdecchia,Luís Cruz,June Sallou,Michelle Lin,James Wickenden,Estelle Hotellier
机构*：Vrije Universiteit Amsterdam, nl†Delft University of Technology, fr§McGill University, ca¶University of Bristol
备注：11 pages, 3 figures, 2 tables. Accepted at the 8th ICT for Sustainability Conference (ICT4S) 2022
链接：点击下载PDF文件
【14】 Adversarial Learning to Reason in an Arbitrary Logic
标题：在任意逻辑中进行推理的对抗性学习
作者：Stanisław J. Purgał,Cezary Kaliszyk
机构*：University of Innsbruck, Austria
Journal-ref：FLAIRS 2022
链接：点击下载PDF文件
【15】 Mix-and-Match: Scalable Dialog Response Retrieval using Gaussian Mixture Embeddings
标题：Mix-and-Match：基于高斯混合嵌入的可扩展对话响应检索
作者：Gaurav Pandey,Danish Contractor,Sachindra Joshi
机构*：IBM Research, India
备注：10 pages, 2 figures
链接：点击下载PDF文件
【16】 Learning to Adapt Clinical Sequences with Residual Mixture of Experts
标题：学会用残差混合的专家适应临床序列
作者：Jeong Min Lee,Milos Hauskrecht
机构*：Department of Computer Science, University of Pittsburgh, Pittsburgh, PA, USA
备注：Accepted at 20th International Conference on Artificial Intelligence in Medicine (AIME) 2022
链接：点击下载PDF文件
【17】 Language Model for Text Analytic in Cybersecurity
标题：网络安全中的文本分析语言模型
作者：Ehsan Aghaei,Xi Niu,Waseem Shadid,Ehab Al-Shaer
机构*：UNC Charlotte, Charlotte, NC, Carnegie Mellon University, Pittsburgh, PA
备注：This is the initial draft of this work and it may contain errors and typos. The revised version has already been submitted to a venue
链接：点击下载PDF文件
【18】 PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model
标题：PP-LiteSeg：一种性能优越的实时语义分割模型
作者：Juncai Peng,Yi Liu,Shiyu Tang,Yuying Hao,Lutao Chu,Guowei Chen,Zewu Wu,Zeyu Chen,Zhiliang Yu,Yuning Du,Qingqing Dang,Baohua Lai,Qiwen Liu,Xiaoguang Hu,Dianhai Yu,Yanjun Ma
机构*：Baidu Inc.
链接：点击下载PDF文件
【19】 Disentangling the Computational Complexity of Network Untangling
标题：解开网络解缠的计算复杂性
作者：Vincent Froese,Pascal Kunz,Philipp Zschoche
机构*：Technische Universit¨at Berlin, Faculty IV, Institute of Software Engineering and Theoretical, Computer Science, Algorithmics and Computational Complexity.
链接：点击下载PDF文件
【20】 Spatio-Temporal Dynamic Graph Relation Learning for Urban Metro Flow Prediction
标题：基于时空动态图关系学习的城市地铁客流预测
作者：Peng Xie,Minbo Ma,Tianrui Li,Shenggong Ji,Shengdong Du,Zeng Yu,Junbo Zhang
链接：点击下载PDF文件
【21】 DAGAM: Data Augmentation with Generation And Modification
标题：DAGAM：通过生成和修改来增强数据
作者：Byeong-Cheol Jo,Tak-Sung Heo,Yeongjoon Park,Yongmin Yoo,Won Ik Cho,Kyungsun Kim
机构*：AI R&D Group, NHN Diquest, Department of Electrical and Computer Engineering and INMC, Seoul National University
链接：点击下载PDF文件
【22】 DeFTA: A Plug-and-Play Decentralized Replacement for FedAvg
标题：DeFTA：FedAvg的即插即用分散式替代
作者：Yuhao Zhou,Minjia Shi,Yuxin Tian,Qing Ye,Jiancheng Lv
机构*：Sichuan University
备注：12 pages, 5 figures
链接：点击下载PDF文件
【23】 A Weakly Supervised Propagation Model for Rumor Verification and Stance Detection with Multiple Instance Learning
标题：基于多实例学习的谣言验证和立场检测的弱监督传播模型
作者：Ruichao Yang,Jing Ma,Hongzhan Lin,Wei Gao
机构*：Hong Kong Baptist University, Hong Kong SAR, China, Beijing University of Posts and Telecommunications, Beijing, China, Singapore Management University
备注：Accepted by SIGIR 2022
链接：点击下载PDF文件
【24】 Bridging the Gap of AutoGraph between Academia and Industry: Analysing AutoGraph Challenge at KDD Cup 2020
标题：弥合学术界与产业界之间的签名鸿沟--解析2020年KDD杯签名挑战赛
作者：Zhen Xu,Lanning Wei,Huan Zhao,Rex Ying,Quanming Yao,Wei-Wei Tu,Isabelle Guyon
机构*：Paradigm, China, Institute of Computing Technology, Chinese Academy of Sciences, China, Stanford University, USA, Tsinghua University, China, ChaLearn, USA, LISNINRIACNRS, University Paris-Saclay, France
备注：arXiv admin note: text overlap with arXiv:2110.05802
链接：点击下载PDF文件
【25】 Distributed Transition Systems with Tags for Privacy Analysis
标题：用于隐私分析的带标签的分布式转换系统
作者：Siva Anantharaman,Sabine Frittella,Benjamin Nguyen
机构*： Universit´e d’Orl´eans (France)
链接：点击下载PDF文件
【26】 Contextual Attention Mechanism, SRGAN Based Inpainting System for Eliminating Interruptions from Images
标题：情境注意机制--基于SRGAN的图像干扰消除修复系统
作者：Narayana Darapaneni,Vaibhav Kherde,Kameswara Rao,Deepali Nikam,Swanand Katdare,Anima Shukla,Anagha Lomate,Anwesh Reddy Paduri
机构*：Director - AIML, Great LearningNorthwestern University, Illinois, USA, Student - AIML, Pune, India, Senior Data Scientist- AIML
链接：点击下载PDF文件
【27】 Banana Sub-Family Classification and Quality Prediction using Computer Vision
标题：基于计算机视觉的香蕉亚科分类与品质预测
作者：Narayana Darapaneni,Arjun Tanndalam,Mohit Gupta,Neeta Taneja,Prabu Purushothaman,Swati Eswar,Anwesh Reddy Paduri,Thangaselvi Arichandrapandian
机构*：Arichandrapandian, Northwestern UniversityGreat Learning, US, -, Great Learning, Bangalore, India
链接：点击下载PDF文件
【28】 Detecting key Soccer match events to create highlights using Computer Vision
标题：使用计算机视觉检测关键足球比赛事件以创建亮点
作者：Narayana Darapaneni,Prashant Kumar,Nikhil Malhotra,Vigneswaran Sundaramurthy,Abhaya Thakur,Shivam Chauhan,Krishna Chaitanya Thangeda,Anwesh Reddy Paduri
机构*： Northwestern UniversityGreat Learning, Evanston, US, -, Great Learning, Bangalore, India
链接：点击下载PDF文件
【29】 FairNeuron: Improving Deep Neural Network Fairness with Adversary Games on Selective Neurons
标题：FairNeuron：通过对选择性神经元的对抗性游戏提高深度神经网络的公平性
作者：Xuanqi Gao,Juan Zhai,Shiqing Ma,Chao Shen,Yufei Chen,Qian Wang
机构*：Xi’an Jiaotong University, Xi’an, China, Rutgers University, United States, Wuhan University, Wuhan, China
链接：点击下载PDF文件
【30】 DouZero+: Improving DouDizhu AI by Opponent Modeling and Coach-guided Learning
标题：DouZero+：通过对手建模和教练引导学习提升抖迪珠AI
作者：Youpeng Zhao,Jian Zhao,Xunhan Hu,Wengang Zhou,Houqiang Li
机构*： Li are with the CAS KeyLaboratory of Technology in Geo-spatial Information Processing and Applica-tion System, Department of Electronic Engineering and Information Science, University of Science and Technology of China
链接：点击下载PDF文件
【31】 Improving Zero-Shot Event Extraction via Sentence Simplification
标题：通过句子简化改进零射事件抽取
作者：Sneha Mehta,Huzefa Rangwala,Naren Ramakrishnan
机构*：Twitter Cortex, George Mason University, Virginia Tech
链接：点击下载PDF文件
【32】 Inferring Rewards from Language in Context
标题：从语境中的语言推断奖赏
作者：Jessy Lin,Daniel Fried,Dan Klein,Anca Dragan
机构*：♦ University of California, Berkeley, ♣ Carnegie Mellon University
备注：ACL 2022. Code and dataset: this https URL
链接：点击下载PDF文件
【33】 Efficient Pragmatic Program Synthesis with Informative Specifications
标题：具有信息规格说明的高效实用程序综合
作者：Saujas Vaduguru,Kevin Ellis,Yewen Pu
机构*：IIIT Hyderabad, Cornell University, Autodesk Research
备注：9 pages, Meaning in Context Workshop 2021
链接：点击下载PDF文件
【34】 Adversarial Robustness through the Lens of Convolutional Filters
标题：基于卷积滤波透镜的对抗性鲁棒性
作者：Paul Gavrikov,Janis Keuper
机构*：IMLA, Offenburg University,CC-HPC, Fraunhofer ITWM,Fraunhofer Research Center ML
备注：Accepted at the CVPR 2022 "The Art of Robustness" Workshop
链接：点击下载PDF文件
【35】 "Does it come in black?" CLIP-like models are zero-shot recommenders
作者：Patrick John Chia,Jacopo Tagliabue,Federico Bianchi,Ciro Greco,Diogo Goncalves
机构*：Coveo, Montreal, Coveo Labs, New York, Bocconi University, Milan, Farfetch, Porto
备注：Pre-print. Accepted ACL 2022 (ECNLP)
链接：点击下载PDF文件
【36】 BeeTS: Smart Distributed Sensor Tuple Spaces combined with Agents using Bluetooth and IP Broadcasting
标题：甜菜：使用蓝牙和IP广播结合代理的智能分布式传感器元组空间
作者：Stefan Bosse
机构*：University of Bremen, Dept. Mathematics & Computer Science, Bremen &, Institute for Digitization, Bremen, Germany
链接：点击下载PDF文件
【37】 Predicting and Explaining Mobile UI Tappability with Vision Modeling and Saliency Analysis
标题：基于视觉建模和显著性分析的移动用户界面触摸性预测与解释
作者：Eldon Schoop,Xin Zhou,Gang Li,Zhourong Chen,Björn Hartmann,Yang Li
机构*：UC Berkeley EECS, Berkeley, CA, USA, Google Research, Mountain View, CA, USA, ResNet, Tappability Prediction, Tappable or Not Tappable, as perceived by users, Concatenate, [H, W,], Features, -dimensional, latent representation, k-Nearest Neighbors, on training dataset
备注：CHI'22
链接：点击下载PDF文件
【38】 Detecting Cloud-Based Phishing Attacks by Combining Deep Learning Models
标题：结合深度学习模型检测基于云的钓鱼攻击
作者：Medha Atre,Birendra Jha,Ashwini Rao
机构*：Eydle Inc.
链接：点击下载PDF文件
【39】 AAAI SSS-22 Symposium on Closing the Assessment Loop: Communicating Proficiency and Intent in Human-Robot Teaming
标题：AAAI SSS-22闭合评估循环研讨会：交流人-机器人团队的熟练程度和意图
作者：Michael Goodrich,Jacob Crandall,Aaron Steinfeld,Holly Yanco
链接：点击下载PDF文件
【40】 A Dempster-Shafer approach to trustworthy AI with application to fetal brain MRI segmentation
标题：可信人工智能的Dempster-Shafer方法及其在胎脑MRI分割中的应用
作者：Lucas Fidon,Michael Aertsen,Florian Kofler,Andrea Bink,Anna L. David,Thomas Deprest,Doaa Emam,Fr'ed'eric Guffens,András Jakab,Gregor Kasprian,Patric Kienast,Andrew Melbourne,Bjoern Menze,Nada Mufti,Ivana Pogledic,Daniela Prayer,Marlene Stuempflen,Esther Van Elslander,Sébastien Ourselin,Jan Deprest,Tom Vercauteren
机构*：Vercauteren, School of Biomedical Engineering & Imaging Sciences, King’s, College London, London, UK, Department of Radiology, University Hospitals Leuven, Leuven, Belgium, Department of Informatics, Technical University Munich, Munich
备注：preprint
链接：点击下载PDF文件
【41】 A deep learning framework for the detection and quantification of drusen and reticular pseudodrusen on optical coherence tomography
标题：光学相干断层扫描中玻璃体和网状假性玻璃体的检测与量化深度学习框架
作者：Roy Schwartz,Hagar Khalid,Sandra Liakopoulos,Yanling Ouyang,Coen de Vente,Cristina González-Gonzalo,Aaron Y. Lee,Robyn Guymer,Emily Y. Chew,Catherine Egan,Zhichao Wu,Himeesh Kumar,Joseph Farrington,Clara I. Sánchez,Adnan Tufail
机构*：Tufail, Moorfields Eye Hospital NHS Foundation Trust, London, UK, Institute of Health Informatics, University College London, London, UK, Quantitative Healthcare Analysis (qurAI) Group, Informatics Institute, University of Amsterdam, Amsterdam, Netherlands
备注：26 pages, 7 figures
链接：点击下载PDF文件
【42】 Zero-shot Blind Image Denoising via Implicit Neural Representations
标题：基于隐式神经表示的零射频盲图像去噪
作者：Chaewon Kim,Jaeho Lee,Jinwoo Shin
备注：8 pages, 3 figures
链接：点击下载PDF文件
【43】 Hospital-Agnostic Image Representation Learning in Digital Pathology
标题：数字病理学中与医院无关的图像表征学习
作者：Milad Sikaroudi,Shahryar Rahnamayan,H. R. Tizhoosh
备注：Accepted for presentation at the 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC'22)
链接：点击下载PDF文件
机器翻译，仅供参考
重大更新！公众号每日速递覆盖arXiv所有方向,涵盖CS|物理|数学|经济|统计|金融|生物|电气等领域。点击查看历史文章列表，可在公众号内订阅#arXiv每日学术速递话题，接收每日推送。点击访问arxivdaily.com每日更新更及时。 |
用Deepseek满血版问问看
